New! View global litigation for patent families

US7760372B2 - Method for automated document selection - Google Patents

Method for automated document selection Download PDF

Info

Publication number
US7760372B2
US7760372B2 US11032898 US3289805A US7760372B2 US 7760372 B2 US7760372 B2 US 7760372B2 US 11032898 US11032898 US 11032898 US 3289805 A US3289805 A US 3289805A US 7760372 B2 US7760372 B2 US 7760372B2
Authority
US
Grant status
Grant
Patent type
Prior art keywords
pages
document
method
proofing
page
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US11032898
Other versions
US20060152748A1 (en )
Inventor
Ann L. McCarthy
Karen M. Braun
Steven J. Harrington
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xerox Corp
Original Assignee
Xerox Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Grant date

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30Information retrieval; Database structures therefor ; File system structures therefor
    • G06F17/3061Information retrieval; Database structures therefor ; File system structures therefor of unstructured textual data
    • G06F17/30705Clustering or classification
    • G06F17/3071Clustering or classification including class or cluster creation or modification

Abstract

Provided is a method for the automated selection of sample documents or pages from a large collection, and more particularly an application of the method in a proof presentment environment—where the method is employed for selection and review of representative or extreme pages from a large document, such as one scheduled for printing. The method characterizes pages or documents in a multi-dimensional vector space based upon a set of characteristics, and then uses clustering techniques to group the pages, enabling the selection of typical pages from the groups, outlier pages from extremes lying outside of the groups, or both typical and outlier pages.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

Reference is made to commonly-assigned, co-pending U.S. patent applications:

Application Ser. No. 10/880,841, entitled “SYSTEM AND METHOD FOR MEASURING AND QUANTIZING DOCUMENT QUALITY,” by Steven J. Harrington et al., filed Jun. 30, 2004;

Application Ser. No. 10/881,792, entitled “SYSTEM AND METHOD FOR MEASURING AND QUANTIZING DOCUMENT QUALITY,” by Steven J. Harrington et al., filed Jun. 30, 2004;

Application Ser. No. 10/880,840, entitled “SYSTEM AND METHOD FOR MEASURING AND QUANTIZING DOCUMENT QUALITY,” by Steven J. Harrington et al., filed Jun. 30, 2004; and

Application Ser. No. 11/032,746, entitled “METHOD FOR PROOFING VARIABLE INFORMATION DOCUMENT RUNS USING DOCUMENT QUALITIES,” by Lisa Purvis et al., filed Jan. 11, 2005,

the disclosure(s) of each of the above-identified applications being hereby incorporated by reference herein.

The method disclosed herein relates to the automated selection of sample documents or pages from a large collection, and more particularly to an application of the method in a proof printing environment where the method is employed for selection of representative or extreme pages from a large document scheduled for printing.

BACKGROUND AND SUMMARY

The following patents or publications are noted, and are hereby incorporated by reference in their entirety:

U.S. Pat. No. 6,581,056 to Rao et al., issued Jun. 17, 2003, describes an information retrieval system and method for conducting a content analysis on a collection of documents; and

U.S. Pat. No. 5,442,778 to Pedersen et al., issued Aug. 15, 1995, teaches a Scatter-Gather browsing tool, and associated method, where a user is presented with descriptions of document groups selected from a document collection. Based upon the descriptions, the user can then selects one or more groups for further study, where the selected groups are then recombined or gathered and re-clustered and presented to the user.

Although the patents above indicate the use of clustering techniques to group documents on a network or database, it is believed that such patents were directed primarily to the textual content of documents, and not to other aspects or characteristics of the information associated with the document, particularly printing characteristics. Moreover, the patents did not proceed so far as to automatically select documents, or pages from documents, but were utilized to assist a user in the identification and review of such documents. The key distinction of the method disclosed herein is that the pages and/or documents are selected using visual appearance criteria—and are not selected as a function of information content.

Disclosed herein is a method for automatically selecting sample documents or pages from a large collection using estimated rendered visual appearance criteria. One particular application of such a method is for selection of one or more representative or extreme pages from a large document scheduled for printing, for proofing purposes. Other applications can include analysis of a large corpus of data within a knowledgebase, as a precursor to preparing the one or more transformations necessary to render the corpus of data to be suitable for presentment.

In accordance with one aspect of the method, characteristics of documents or pages are represented in a multidimensional vector space, and clustering techniques are used to group together similar pages. Characteristics may include content metadata such as color encoding descriptors and font names, or page information such as area coverage, font size, image count, etc., that are then represented and grouped. Typical pages can be chosen from the centers of identified clusters, whereas exceptional pages can be selected from cluster extrema. In this manner, both the quality of the majority and the quality risk of the outlier pages can be assessed. The multidimensional vector space can be tailored according to the application requirements. In the case of a pre-press review or proofing system, proofing requirements might dictate that the vector space be representative of printing characteristics (color imagery, layout, etc.) as will be described in more detail below.

It is anticipated that the described method will ease the task of visually proofing large and/or variable information documents, promising substantial savings in time and cost over the current manual proofing of large documents. As it is reasonable to print only selected pages for proofing purposes, and proof prints of every page may not be required, a combination of typical and extreme pages will suffice, and the described method may be employed to select representative or typical and exceptional pages for proofing. One embodiment of the method described is for production workflowsi (e.g., DigiPath, DocuSP, Enterprise Output Management System) and other workflow management systems—particularly those related to pre-press or pre-flight analysis, document creation and layout applications, variable imaging applications, and digital front ends.

Accordingly, a method is described for automatically selecting sample pages from a large document for proofing purposes. More specifically, the method characterizes pages in a multidimensional vector space and then uses a cluster-analysis technique to group the pages so that representative pages from at least one group (or a page not within a group) may be automatically selected for proofing.

Disclosed in an embodiment herein is a method for automated document subset selection from a stored body of knowledge, comprising the steps of: accessing the body of knowledge, including a plurality of documents therein; characterizing at least a portion of the body of knowledge in a characterization space; grouping the documents into a plurality of groups; and automatically selecting, based upon said grouping, a subset of the body of knowledge for presentment, including transform preparation for rendering and proofing.

Disclosed in another embodiment herein is a method for automated selection of proofing pages from a print job, comprising the steps of: receiving a multi-page document for printing; characterizing a plurality of pages of the multi-page document in a characterization space; grouping at least some of the plurality of pages into at least one group; and selecting, based upon the grouping, at least one page for presentment as a proof page.

Disclosed in yet another embodiment herein is, in electronic document processing, a method for pre-flight checking at least one electronic document intended for printing including the steps of: characterizing a plurality of pages of the document in a characterization space; grouping at least some of the plurality of pages into at least one group; and selecting, based upon the grouping, at least one page for presentment as a proof page.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a general flow diagram illustrating steps of the disclosed method in association with the flow of information;

FIG. 2 is a representation of an exemplary data flow and clustering step of the method of FIG. 1;

FIG. 3 is an exemplary workflow for a print proofing method; and

FIG. 4 is an exemplary illustration of a user interface for an embodiment illustrating aspects of the method described herein.

The following disclosure will be characterized in connection with a preferred embodiment, however, it will be understood that there is no intent to limit the disclosure or scope to the embodiment described. On the contrary, the intent is to cover all alternatives, modifications, and equivalents as may be included within the spirit and scope of the appended claims.

DETAILED DESCRIPTION

For a general understanding of the method and described embodiments, reference is made to the drawings. In the drawings, like reference numerals have been used throughout to designate identical elements. As used herein the term document is used not only to represent, what is typically understood as a single or multi-page collection, but also is intended to represent components of documents which may themselves be combined to produce a conventional document. Accordingly, unless otherwise indicated, the term “document” is intended to cover a broad range of possible items, from document components, to fully assembled, multi-page collections of information.

As will be further appreciated the method described herein can be carried out on a production or commercial printing system, and more particularly, on one or more processors associated with a commercial printing system. For example, the method can be implemented largely as a sequence of programmed operations carried out by a computer processor, such as Pentium® processor running a Microsoft® Windows-based operating system with 128 MB RAM or thereabout. Furthermore, the method described below may be implemented in association with preflight software (i.e., the Enfocus PITSTOP™ software, or possibly MARKZWARE™ Flightcheck Professional).

Referring to FIG. 1, there is depicted a flowchart and associated dataflow illustration representing the general steps in a method for automated document subset selection from a stored body of knowledge. As will be further described in accordance with a print workflow embodiment, the method comprises accessing, in step 110, a body of knowledge 140, including a plurality of documents therein. As noted above, the term “document” is intended to be construed broadly, and the body of knowledge may include single and multi-page documents as well as document components. Next, the pages are characterized at step 114, where the documents are analyzed and particular characteristics such as content appearance metadata (font name, image encoding, etc.), margins, colors and other page characteristics (N0, N1, . . . ) are similarly represented. In one embodiment, the characterization is accomplished with respect to a multidimensional characterization space represented as 150.

After the documents are characterized, they may be further associated or grouped with one another at step 118 using, for example, clustering techniques to form a plurality of groups 160. Finally, at step 122, one or more groups 164 may be selected, based upon said grouping, for presentment rendering transform preparation and proofing—where presentment rendering may include any of various means or methods for interpreting document and page appearance and rendering instructions, preparing rendering instructions, and transforming for presentment one or more documents from the selected group according to said rendering instructions.

More specifically, one aspect of the method contemplates the possibility of characterizing the group of documents within the body of knowledge based upon the transform required to render (e.g., print) the document. In other words, characterize and group documents according to the distinct transforms required for rendering and presentment (e.g., group together all pages containing a particular RGB color encoding), and select one of the group for proofing (e.g., testing the specific color rendering transformation that is required to modify the particular RGB colors for CMYK printing). Similarly, all pages containing a particular printer specific (e.g., CMYK) encoding could be grouped together, and one of the group selected and used to test the transformation (e.g., CMYK transformation to sRGB) required for web presentment. Such an aspect could, therefore, include in the selection of documents for proofing, an identified expectation to apply a distinct rendering transform in preparation for rendering or presentment. Similarly, the same aspect could be employed to “test” that the rendering transform selected is appropriate for the document, and the system may be employed to proof using the transform just to be sure. In this way, the proofing intent (as described with respect to FIG. 3) would include testing of the rendering transform for the selected group.

With respect to step 114, for characterizing at least a portion of the body of knowledge, the step would process each document in the body of knowledge. Moreover, the step would further include determining, for each document, a plurality of vectors to represent each of a plurality of characteristics of the documents, and representing each in a multidimensional vector space based upon the plurality of vectors.

Furthermore, relative to step 118, grouping the documents further includes analyzing clusters within the multidimensional vector space to determine characteristics common to each cluster and grouping those documents or pages having similar characteristics. And, the step (122) of automatically selecting a subset of the body of knowledge for presentment further comprises the step of identifying a representative document within a cluster. Alternatively, selection step 122 may identify an atypical document outside of a cluster. It should be appreciated that these alternatives are not necessarily mutually exclusive, and in certain circumstances, it may be desirable to select within and outside of a group or cluster, as will be described below.

An example of the general use of the disclosed method may be a web-based interface or application that presents a descriptions of items from a catalog, including product specifications, company information, etc. in response to a pre-specified criteria or the like. More specifically, product specification or other characteristics may be employed for the grouping of the catalog items, and then the selection of specific groups or members of the group completed to present the information to a user—via a display, print, etc.

Similarly, the system could be employed in the generation of web pages, where there could be a variety of web pages in the body of knowledge 140 and some subsets of those web pages could be automatically generated from databases of content. The proofing methodology described with respect to steps 110-122 could then be applied to the associated web portal to sample the look of the web pages that might be seen. As will be appreciated the use of the general method is, therefore, not limited to proof printing, but may also cover cases where selections are presented in other forms, not limited to actual printing of pages/documents.

Accordingly, FIGS. 1 and 2 illustrate a general method for automatically selecting sample pages from a large document for proofing purposes. The method characterizes pages in a multidimensional vector space 210 and then uses known cluster-analysis techniques to group the documents or pages (Groups A-F). For example, an agglomerative hierarchical clustering technique, such as a graph method, may be used. An initial pattern matrix (N×N matrix of similarity values) can be determined by extracting a maximum range of characteristic feature occurrences from the documents in the body of knowledge, and can be used to determine the usefulness of various characteristic features as clustering criteria before the clustering algorithm is initiated. Attention to the weights on the graph links can be used to control the resulting degree of cluster inclusiveness. The clustering method selected should allow for mixed discrete (alike or not alike) characteristic similarity assessment—perhaps as intermediate constraints, and continuous—similarity distance-based—characteristic similarity assessment. Given the agglomerative hierarchy of clusters, the best clustering for proofing or presentment transform preparation can be chosen via user preferences.

Typical documents can be chosen from the centers of the clustered groups 230. Exceptional documents 240, lying outside the clusters can be also determined by looking for the extremes in the chosen dimensions of the vector space, and/or by looking for document pages that lie far from cluster centers.

The characteristics used for the vector space can be parameters such as margin size, but in order to be applied to all pages, regardless of content, characteristics are better taken to be higher level document properties, such as area coverage, balance, average font size, image fraction, image count, color-rendering predictability, and so on. Vector space dimension parameters can be re-ordered and prioritized differently to satisfy the distinct needs of different proofing iterations. In another embodiment, the characteristics used to characterize pages or documents in a proofing implementation include the various characteristics set forth and measured or quantized by Harrington et al. and Purvis et al. in the cross-referenced applications incorporated by reference above.

In one useful scenario, a set of vector space dimensions might be comprised of dimensions corresponding to each of a) number of distinct font names, b) number of font styles, c) number of distinct Pantone colors, d) and number of raster image objects. In this case, the resulting four dimensional vector space could be used to identify components, pages or documents containing a maximum number of Pantone colors in combination with images, pages containing a variety of font names and styles, etc.

Referring next to FIG. 3, there is depicted a method for preparing a document for printing, including pre-flight check of the document. In response to receiving a print job submission 310, the job is first checked to see if it is complete (e.g., includes all necessary information) at step 314 and is then scheduled for printing or production at step 318. Next, in pre-flight checking step 330, one or more of a plurality of checks (332, 334 and 336) are performed. In general, these steps employ the automated selection of proofing pages from a print job. More specifically, the checks include receiving a multi-page document as part of the print job, and then characterizing the pages of the multi-page document in a characterization space as described above (step 114). Once characterized, the pages are grouped (step 118) and selected (step 122) in accordance with the requirements of the particular check or proofing step being executed, typically such that pages at risk for rendering quality failures are identified.

Proofing of a document may take place in several iterations or passes, for example the steps set forth in 330. Moreover, proofing may or may not include actual printing of the document, or components thereof. In other words, although selected for proofing review, it may be possible to review the selected pages by various means of presentment, including visual display on electronic medium (e.g., displays, televisions). While one pass may involve inspection of every page of a document, some proofing passes may only require representative pages, or alternatively, pages with particular exceptional or extreme attributes. For example, an early proofing pass may be looking for properties that are expected to be common across many pages, and thus looking at representative pages is sufficient. Another proofing pass may be looking at properties that pertain to only a few pages. And, as described above, the characteristics may include the rendering transform in preparation for presentment, wherein the characterization and grouping include the ability to select documents having distinct rendering transforms.

The cross-referenced application to Purvis et al. suggests that document design qualities such as alignment, balance, and legibility could provide valuable information to the proofer, but further, extreme cases of these qualities might be used to select instances of a variable information document for proofing. In other words, using such qualities as alignment, balance, and legibility, the present method may be employed automatically select one or more pages representative of typical or extreme examples of such qualities.

A variable information document poses a similar problem where it is typically impractical to proof every possible page. Selecting instances of a variable information document is slightly different and may actually be a simpler problem, especially when the variable content substitution is constrained to a particular document layout. In this case all of the document instances are similar and a proof operation might seek the extreme rather than the representative cases.

On the other hand, when variable information is combined to create documents that do not conform to a single document layout (e.g., when automated document composition includes complex text reflow), then proofing both representative and extreme subsets of the possible instances can be of benefit. Examples of document design qualities are presented in the above-identified applications. These design qualities have the property that they are defined for any document content and style. They can be calculated for any arbitrary document. Some of these qualities are intended to be calculated for individual pages, while others can be employed on a page-by-page basis by treating each page as a one-page document.

Other qualities that are well defined for any page can be constructed as well. Such qualities are more useful than specific parameters such as image size or heading font that may have problems identifying pages for proofing if there are no images or headings. The method described herein further contemplates using qualities defined for any page (such as the design qualities) in the procedure for selecting representative pages. The qualities to be used in characterizing the pages are calculated for each page and a characterization vector for the page is formed from the quality values. Each page is thus represented by a point in a multidimensional characterization space based upon the qualities. Well known cluster analysis methods can then be applied to determine clusters or groups of points within the space. The calculation of clusters may also be configured to satisfy the purpose of a particular proofing iteration as described above and illustrated in FIGS. 2 and 3.

Referring next to FIG. 4, there is shown an exemplary user interface 408 that illustrates some aspects of the method described herein. More specifically, FIG. 4 shows an Adobe Acrobat® window 410 that was opened to review a PDF document such as the 100-page Xerox 2003 Annual report. Subsequently, the FreeFlow Subset Proofing add-in was initiated and dialog box 420 opened. To process the PDF of the annual report document, the objects within the PDF document file were reviewed and the occurrences of various object types (text fonts, font colors, images, etc.) were identified. In response to the user's selection of check boxes 430 and 432 (fonts and images, respectively) to indicate what was to be selected for proofing, the add-in software reviewed the PDF objects and identified the first occurrence of any new object meeting either of the selected criteria. The list within region 440 provides details as to the first occurrence of each item type (e.g., each new font type or color), and also provides a comprehensive listing of each document page (total of 18 pages) selected from the larger document for proofing purposes. Furthermore, the highlighted item in region 440 corresponds with displayed page 4.

In region 440, the first occurrence of each new font, and each unique image is represented and is employed for selection of the subset of pages to be used for proofing. In other words, the first time the font Univers-CondensedBold occurs is at page 4 of the PDF document, and is indicated within the dashed outline region 450. Although the example depicted utilizes a first-occurrence selection criteria to select pages for proofing, it will be appreciated that the afore-described cluster-based analysis of pages and documents to identify typical pages or extreme pages may be substituted. It is, however, possible to employ one or more user preferences, as set forth in dialog box 420, to facilitate proofing. For example, as indicated with respect to FIG. 3, the Fonts and Images checkboxes may be replaced with Layout, Image Quality and Text & Line-Art Content/Detail as may be considered to specify the type of proofing operation being conducted. Thus, predefined criteria for a particular proofing operation of proofing pass may be employed to determine the nature of document pages to be selected for proofing.

For example, referring again to FIG. 3, when developing a print job there are typically proofing steps in the workflow that confirm that the printed document will appear as expected. There may be several proofing iterations, where one proofing iteration checks that page presentment layout (e.g. geometric relationships between objects including margins, fonts, etc.) is correct, step 332; another proofing iteration that checks color element quality, step 334; and yet another proofing iteration that considers text rendering and page flow quality, step 336. When a document is large (e.g., tens of pages), visual evaluation of every page at every iteration would be costly and time consuming. Hence, the described method may be employed as a means of controlling and minimizing print quality risk, in that representative pages are and have been reviewed for pre-flight or proofing purposes before an entire large job is printed (step 340, prints 350). Further to the examples set forth above, it is also contemplated that the preflight checking steps may include an automated proof selection directed to characteristics including layout (e.g., margin size, balance, font, font size, font reflow, and alignment) and color reproduction (e.g., area coverage, image fraction, image count, color-rendering predictability).

Returning to FIG. 4, the dialog box 420 further illustrates the manner in which one or more pages of the document being submitted for proofing may be reviewed. In addition to automatically selecting pages for proofing, the method may further enable the display of such pages in an associated document review system. And, as illustrated by the outlining in region 450, the system may specifically indicate in the native document display software, the region or aspect of the page that was selected for particular proofing in the event that an atypical or extrema is noted relative to the page.

In summary, the methods described herein enable the automated selection of sample pages from a large document or body of knowledge for proofing purposes. More specifically, the method characterizes pages in a multidimensional vector space and then uses a cluster-analysis technique to group the pages so that representative pages from at least one group (and atypical pages with high quality risk not within a group) may be automatically selected for proofing.

The claims, as originally presented and as they may be amended, encompass variations, alternatives, modifications, improvements, equivalents, and substantial equivalents of the embodiments and teachings disclosed herein, including those that are presently unforeseen or unappreciated, and that, for example, may arise from applicants/patentees and others.

Claims (13)

1. A method for automated selection of proofing pages from a print job, comprising:
receiving a multi-page document for printing;
characterizing a plurality of pages of the multi-page document in a characterization space;
grouping at least some of the plurality of pages into at least one group; and
selecting, based upon the grouping, at least one but less than all pages in the multi-page document for presentment as proofing pages.
2. The method of claim 1, wherein selecting at least one page comprises selecting, from the group, a page that is representative of the group.
3. The method of claim 1, wherein selecting at least one page comprises selecting a page that is an outlier from at least one group.
4. The method of claim 1, wherein selecting at least one page comprises selecting a page from the group based upon its order of occurrence in the document.
5. A method for automated selection of proofing pages from a print job, comprising:
receiving a multi-page document for printing;
characterizing a plurality of pages of the multi-page document in a characterization space, wherein characterizing a plurality of pages, further comprises locating, in the characterization space, the position of a page as a function of the value of at least two document characteristics;
grouping at least some of the plurality of pages into at least one group; and
selecting, based upon the grouping, at least one page for presentment.
6. The method of claim 5, wherein the document characteristics include layout and color reproduction.
7. The method of claim 6, wherein the document layout characteristics are selected from the group consisting of margin size, balance, font, average font size, and alignment.
8. The method of claim 6, wherein the document color reproduction characteristics are selected from the group consisting of area coverage, image fraction, image count, and color-rendering predictability.
9. The method of claim 5, wherein the document characteristics include at least one font characteristic.
10. The method of claim 5, wherein the document characteristics include a rendering transform to be applied to the document in preparation for presentment.
11. The method of claim 5, wherein selecting, based upon the grouping, at least one page for presentment further includes printing the at least one page as a proof page.
12. A method for automated selection of proofing pages from a print job, comprising:
receiving a multi-page document for printing;
characterizing a plurality of pages of the multi-page document in a characterization space;
grouping at least some of the plurality of pages into at least one group;
selecting, based upon the grouping, at least one but less than all pages in the multi-page document for presentment as proofing pages; and
further comprising identifying the proofing intent and, completing the grouping in accordance with the proofing intent.
13. The method of claim 12, wherein the proofing intent further includes identification of at least one rendering transform for a group.
US11032898 2005-01-11 2005-01-11 Method for automated document selection Active 2029-03-17 US7760372B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US11032898 US7760372B2 (en) 2005-01-11 2005-01-11 Method for automated document selection

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US11032898 US7760372B2 (en) 2005-01-11 2005-01-11 Method for automated document selection
JP2006004087A JP2006195994A5 (en) 2006-01-11
US12796234 US8045188B2 (en) 2005-01-11 2010-06-08 Method for automated document selection
JP2011158769A JP5058363B2 (en) 2005-01-11 2011-07-20 Automatic document selection method

Publications (2)

Publication Number Publication Date
US20060152748A1 true US20060152748A1 (en) 2006-07-13
US7760372B2 true US7760372B2 (en) 2010-07-20

Family

ID=36652923

Family Applications (2)

Application Number Title Priority Date Filing Date
US11032898 Active 2029-03-17 US7760372B2 (en) 2005-01-11 2005-01-11 Method for automated document selection
US12796234 Active US8045188B2 (en) 2005-01-11 2010-06-08 Method for automated document selection

Family Applications After (1)

Application Number Title Priority Date Filing Date
US12796234 Active US8045188B2 (en) 2005-01-11 2010-06-08 Method for automated document selection

Country Status (2)

Country Link
US (2) US7760372B2 (en)
JP (1) JP5058363B2 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070226208A1 (en) * 2006-03-23 2007-09-27 Fujitsu Limited Information retrieval device
US20080317337A1 (en) * 2007-06-25 2008-12-25 Yizhou Wang System and method for decomposing a digital image
US20100110458A1 (en) * 2008-10-31 2010-05-06 Brother Kogyo Kabushiki Kaisha Device for setting color print limit mode according to preference set on per-page basis
US20100268713A1 (en) * 2005-01-11 2010-10-21 Xerox Corporation Method for automated document selection

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB0518262D0 (en) * 2005-09-08 2005-10-19 Hewlett Packard Development Co Flows for variable-data printing
US8035855B2 (en) * 2008-02-01 2011-10-11 Xerox Corporation Automatic selection of a subset of representative pages from a multi-page document
US8780365B2 (en) * 2008-05-07 2014-07-15 Xerox Corporation Printing system with dynamic sample page preview
US8352856B2 (en) * 2009-11-11 2013-01-08 Xerox Corporation Systems and methods to resize document content
US8625165B2 (en) * 2010-06-22 2014-01-07 Microsoft Corporation Optimized font subsetting for a print path
US8910041B1 (en) * 2012-02-23 2014-12-09 Google Inc. Font substitution using unsupervised clustering techniques
US9706064B2 (en) 2015-09-29 2017-07-11 Xerox Corporation Pausing printing for preview of documents printed using remote server-based print queues

Citations (34)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4941057A (en) * 1988-10-24 1990-07-10 Xerox Corporation Digital image proofing
US5333069A (en) * 1992-02-10 1994-07-26 Eastman Kodak Company Technique for use in conjunction with an imaging system for providing an appearance match between two images and for calibrating the system thereto
US5424945A (en) 1993-08-31 1995-06-13 Xerox Corporation System for evaluating a psychological effect of a document
US5442778A (en) 1991-11-12 1995-08-15 Xerox Corporation Scatter-gather: a cluster-based method and apparatus for browsing large document collections
US5600732A (en) 1994-12-08 1997-02-04 Banctec, Inc. Document image analysis method
US5659766A (en) * 1994-09-16 1997-08-19 Xerox Corporation Method and apparatus for inferring the topical content of a document based upon its lexical content without supervision
US5687250A (en) 1994-02-14 1997-11-11 International Business Machines Corporation Image quality analysis method and apparatus
US5774888A (en) * 1996-12-30 1998-06-30 Intel Corporation Method for characterizing a document set using evaluation surrogates
US5937084A (en) * 1996-05-22 1999-08-10 Ncr Corporation Knowledge-based document analysis system
US5963641A (en) * 1995-09-12 1999-10-05 Markzware, Inc. Device and method for examining, verifying, correcting and approving electronic documents prior to printing, transmission or recording
US5990931A (en) * 1996-04-10 1999-11-23 Vtel Corporation Automatic display update of still frame images for videoconferencing
EP0986270A2 (en) 1998-09-10 2000-03-15 Tektronix, Inc. Picture quality measurement using blockiness
US6247011B1 (en) * 1997-12-02 2001-06-12 Digital-Net, Inc. Computerized prepress authoring for document creation
EP1109132A2 (en) 1999-12-14 2001-06-20 Eastman Kodak Company Method for automatic assessment of emphasis and appeal in consumer images
EP1168245A2 (en) 2000-06-23 2002-01-02 Eastman Kodak Company Method for varying the number, size and magnification of photographic prints based on image emphasis and appeal
US6345130B1 (en) 1996-08-28 2002-02-05 Ralip International Ab Method and arrangement for ensuring quality during scanning/copying of images/documents
US20020191219A1 (en) 2001-05-16 2002-12-19 Xerox Corporation Method and apparatus for variable data document printing
US20030051216A1 (en) 2001-09-10 2003-03-13 Hsu Liang H. Automatic validation method for multimedia product manuals
US6571000B1 (en) 1999-11-29 2003-05-27 Xerox Corporation Image processing algorithm for characterization of uniformity of printed images
US6581056B1 (en) 1996-06-27 2003-06-17 Xerox Corporation Information retrieval system providing secondary content analysis on collections of information objects
US20030140307A1 (en) 2002-01-22 2003-07-24 International Business Machines Corporation Method and system for improving data quality in large hyperlinked text databases using pagelets and templates
US20030160975A1 (en) * 2002-02-26 2003-08-28 Skurdal Vincent C. N-up printing methods and systems
US20030202684A1 (en) 2002-04-30 2003-10-30 Beckman Orhan E. Print approval of variable data documents
US20030229543A1 (en) 2002-06-10 2003-12-11 Zimmerman Shannon M. Centralized management of packaging data with rule-based content validation
US20040039990A1 (en) 2002-03-30 2004-02-26 Xorbix Technologies, Inc. Automated form and data analysis tool
US20040066527A1 (en) 2002-10-02 2004-04-08 Nexpress Solutions Llc Finish verification in printing
US20040068692A1 (en) 2000-12-01 2004-04-08 Jinshu Cho Data check supporting server
US20040078337A1 (en) 2001-08-06 2004-04-22 King Shawn L. Electronic document management system and method
US20040151399A1 (en) 2003-01-30 2004-08-05 Skurdal Vincent C. Positioning images in association with templates
US7024022B2 (en) 2003-07-30 2006-04-04 Xerox Corporation System and method for measuring and quantizing document quality
US20060080311A1 (en) * 2004-10-12 2006-04-13 Ut-Battelle Llc Agent-based method for distributed clustering of textual information
US7171618B2 (en) 2003-07-30 2007-01-30 Xerox Corporation Multi-versioned documents and method for creation and use thereof
US7391885B2 (en) 2003-07-30 2008-06-24 Xerox Corporation Method for determining overall effectiveness of a document
US7451140B2 (en) 2005-01-11 2008-11-11 Xerox Corporation System and method for proofing individual documents of variable information document runs using document quality measurements

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5634021A (en) * 1991-08-15 1997-05-27 Borland International, Inc. System and methods for generation of design images based on user design inputs
JP3464343B2 (en) * 1996-04-17 2003-11-10 株式会社図研 Document editing apparatus
JP2000268040A (en) * 1999-03-15 2000-09-29 Ntt Data Corp Information classifying system
JP2001256244A (en) * 2000-03-14 2001-09-21 Fuji Xerox Co Ltd Device and method for sorting image data
US6895552B1 (en) 2000-05-31 2005-05-17 Ricoh Co., Ltd. Method and an apparatus for visual summarization of documents
JP4023075B2 (en) * 2000-07-10 2007-12-19 富士ゼロックス株式会社 Image acquisition device
JP3824209B2 (en) * 2001-04-18 2006-09-20 三菱電機株式会社 Document automatic dividing device
JP4241115B2 (en) * 2003-03-18 2009-03-18 富士ゼロックス株式会社 Document filing apparatus
JP2004288015A (en) * 2003-03-24 2004-10-14 Fuji Xerox Co Ltd Document filing device and document dividing method
US7548910B1 (en) * 2004-01-30 2009-06-16 The Regents Of The University Of California System and method for retrieving scenario-specific documents
US7818456B2 (en) * 2004-06-24 2010-10-19 International Business Machines Corporation Method and system for processing a file attached to an electronic document
US7760372B2 (en) 2005-01-11 2010-07-20 Xerox Corporation Method for automated document selection

Patent Citations (45)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4941057A (en) * 1988-10-24 1990-07-10 Xerox Corporation Digital image proofing
US5442778A (en) 1991-11-12 1995-08-15 Xerox Corporation Scatter-gather: a cluster-based method and apparatus for browsing large document collections
US5333069A (en) * 1992-02-10 1994-07-26 Eastman Kodak Company Technique for use in conjunction with an imaging system for providing an appearance match between two images and for calibrating the system thereto
US5424945A (en) 1993-08-31 1995-06-13 Xerox Corporation System for evaluating a psychological effect of a document
US5687250A (en) 1994-02-14 1997-11-11 International Business Machines Corporation Image quality analysis method and apparatus
US5659766A (en) * 1994-09-16 1997-08-19 Xerox Corporation Method and apparatus for inferring the topical content of a document based upon its lexical content without supervision
US5600732A (en) 1994-12-08 1997-02-04 Banctec, Inc. Document image analysis method
US5963641A (en) * 1995-09-12 1999-10-05 Markzware, Inc. Device and method for examining, verifying, correcting and approving electronic documents prior to printing, transmission or recording
US5990931A (en) * 1996-04-10 1999-11-23 Vtel Corporation Automatic display update of still frame images for videoconferencing
US5937084A (en) * 1996-05-22 1999-08-10 Ncr Corporation Knowledge-based document analysis system
US6581056B1 (en) 1996-06-27 2003-06-17 Xerox Corporation Information retrieval system providing secondary content analysis on collections of information objects
US6345130B1 (en) 1996-08-28 2002-02-05 Ralip International Ab Method and arrangement for ensuring quality during scanning/copying of images/documents
US5774888A (en) * 1996-12-30 1998-06-30 Intel Corporation Method for characterizing a document set using evaluation surrogates
US6247011B1 (en) * 1997-12-02 2001-06-12 Digital-Net, Inc. Computerized prepress authoring for document creation
EP0986270A2 (en) 1998-09-10 2000-03-15 Tektronix, Inc. Picture quality measurement using blockiness
US6795580B1 (en) 1998-09-10 2004-09-21 Tektronix, Inc. Picture quality measurement using blockiness
US6571000B1 (en) 1999-11-29 2003-05-27 Xerox Corporation Image processing algorithm for characterization of uniformity of printed images
EP1109132A2 (en) 1999-12-14 2001-06-20 Eastman Kodak Company Method for automatic assessment of emphasis and appeal in consumer images
US6671405B1 (en) 1999-12-14 2003-12-30 Eastman Kodak Company Method for automatic assessment of emphasis and appeal in consumer images
US6748097B1 (en) 2000-06-23 2004-06-08 Eastman Kodak Company Method for varying the number, size, and magnification of photographic prints based on image emphasis and appeal
EP1168245A2 (en) 2000-06-23 2002-01-02 Eastman Kodak Company Method for varying the number, size and magnification of photographic prints based on image emphasis and appeal
US20040068692A1 (en) 2000-12-01 2004-04-08 Jinshu Cho Data check supporting server
US20020191219A1 (en) 2001-05-16 2002-12-19 Xerox Corporation Method and apparatus for variable data document printing
US20040078337A1 (en) 2001-08-06 2004-04-22 King Shawn L. Electronic document management system and method
US20030051216A1 (en) 2001-09-10 2003-03-13 Hsu Liang H. Automatic validation method for multimedia product manuals
US20030140307A1 (en) 2002-01-22 2003-07-24 International Business Machines Corporation Method and system for improving data quality in large hyperlinked text databases using pagelets and templates
US20030160975A1 (en) * 2002-02-26 2003-08-28 Skurdal Vincent C. N-up printing methods and systems
US20040039990A1 (en) 2002-03-30 2004-02-26 Xorbix Technologies, Inc. Automated form and data analysis tool
US7184168B2 (en) * 2002-04-30 2007-02-27 Hewlett-Packard Development Company, L.P. Print approval of variable data documents
US20030202684A1 (en) 2002-04-30 2003-10-30 Beckman Orhan E. Print approval of variable data documents
US20030229543A1 (en) 2002-06-10 2003-12-11 Zimmerman Shannon M. Centralized management of packaging data with rule-based content validation
US20040066527A1 (en) 2002-10-02 2004-04-08 Nexpress Solutions Llc Finish verification in printing
US20040151399A1 (en) 2003-01-30 2004-08-05 Skurdal Vincent C. Positioning images in association with templates
US7035439B2 (en) 2003-07-30 2006-04-25 Xerox Corporation System and method for measuring and quantizing document quality
US20070061384A1 (en) 2003-07-30 2007-03-15 Xerox Corporation Multi-versioned documents and method for creation and use thereof
US7391885B2 (en) 2003-07-30 2008-06-24 Xerox Corporation Method for determining overall effectiveness of a document
US7072495B2 (en) 2003-07-30 2006-07-04 Xerox Corporation System and method for measuring and quantizing document quality
US7092552B2 (en) 2003-07-30 2006-08-15 Xerox Corporation System and method for measuring and quantizing document quality
US7092551B2 (en) 2003-07-30 2006-08-15 Xerox Corporation System and method for measuring and quantizing document quality
US7095877B2 (en) 2003-07-30 2006-08-22 Xerox Corporation System and method for measuring and quantizing document quality
US7171618B2 (en) 2003-07-30 2007-01-30 Xerox Corporation Multi-versioned documents and method for creation and use thereof
US7024022B2 (en) 2003-07-30 2006-04-04 Xerox Corporation System and method for measuring and quantizing document quality
US7035438B2 (en) 2003-07-30 2006-04-25 Xerox Corporation System and method for measuring and quantizing document quality
US20060080311A1 (en) * 2004-10-12 2006-04-13 Ut-Battelle Llc Agent-based method for distributed clustering of textual information
US7451140B2 (en) 2005-01-11 2008-11-11 Xerox Corporation System and method for proofing individual documents of variable information document runs using document quality measurements

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
Engledrum; Image quality modeling: where are we?; IS&T's 1999 PICS Conference; 251-255.
Flightcheck 5 Professional-User Manual; Markzware, Inc.; c. 1993-2003 USPatent 5963641.
Flightcheck 5 Professional—User Manual; Markzware, Inc.; c. 1993-2003 USPatent 5963641.
Govindaraju et al.; Assessment of image quality to predict readability of documents; SPIE vol. 2660/333-342; 1996.
Shin et al.; Predicting customer preference from objective image quality metrics for monochrome document products; SPIE vol. 5294/ 155-164; 2004.

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8045188B2 (en) 2005-01-11 2011-10-25 Xerox Corporation Method for automated document selection
US20100268713A1 (en) * 2005-01-11 2010-10-21 Xerox Corporation Method for automated document selection
US20070226208A1 (en) * 2006-03-23 2007-09-27 Fujitsu Limited Information retrieval device
US20080317337A1 (en) * 2007-06-25 2008-12-25 Yizhou Wang System and method for decomposing a digital image
US7876958B2 (en) * 2007-06-25 2011-01-25 Palo Alto Research Center Incorporated System and method for decomposing a digital image
US20110116715A1 (en) * 2007-06-25 2011-05-19 Palo Alto Research Center Incorporated Computer-Implemented System And Method For Recognizing Patterns In A Digital Image Through Document Image Decomposition
US8139865B2 (en) 2007-06-25 2012-03-20 Palo Alto Research Center Incorporated Computer-implemented system and method for recognizing patterns in a digital image through document image decomposition
US20100110458A1 (en) * 2008-10-31 2010-05-06 Brother Kogyo Kabushiki Kaisha Device for setting color print limit mode according to preference set on per-page basis
US8384962B2 (en) * 2008-10-31 2013-02-26 Brother Kogyo Kabushiki Kaisha Device for setting color print limit mode according to preference set on per-page basis

Also Published As

Publication number Publication date Type
US8045188B2 (en) 2011-10-25 grant
JP2006195994A (en) 2006-07-27 application
US20100268713A1 (en) 2010-10-21 application
JP5058363B2 (en) 2012-10-24 grant
JP2011258215A (en) 2011-12-22 application
US20060152748A1 (en) 2006-07-13 application

Similar Documents

Publication Publication Date Title
US7272269B2 (en) Image processing apparatus and method therefor
US20040212815A1 (en) Converted digital colour image with improved colour distinction for colour-blinds
US5963641A (en) Device and method for examining, verifying, correcting and approving electronic documents prior to printing, transmission or recording
US7020838B2 (en) System and method for identifying line breaks
US20060279758A1 (en) Imaging device, control method, and program
US6895552B1 (en) Method and an apparatus for visual summarization of documents
US6476930B1 (en) Output processing and merging of hybrid electronic documents
US20100098343A1 (en) Modeling images as mixtures of image models
US20050128516A1 (en) Document processing apparatus and document processing method
US20090110288A1 (en) Document processing apparatus and document processing method
US6650431B1 (en) Processing documents with multiple output devices
US20040083430A1 (en) Method and apparatus to process portable document format data containing transparency
US6549654B1 (en) Image processing method and apparatus and storage medium storing processes of executing the method
US20040220898A1 (en) Information processing apparatus, method, storage medium and program
US7376272B2 (en) Method for image segmentation to identify regions with constant foreground color
US5835634A (en) Bitmap comparison apparatus and method using an outline mask and differently weighted bits
US7391529B2 (en) Apparatus and method for managing and using reusable document components during the process of dynamic document construction
US5835098A (en) Method and system for managing color profiles in a document for making the document portable to other systems
US6175843B1 (en) Method and system for displaying a structured document
US20050154980A1 (en) System and method for dynamic document layout
US5349452A (en) Image processing system capable of attaining color coincidence between input and output images
US6446099B1 (en) Document matching using structural information
US6480291B1 (en) Font management system that provides for synchronization of fonts among resources
US20040205081A1 (en) Method and apparatus for classifying elements of a document
US7375842B2 (en) Variable data printing using variants

Legal Events

Date Code Title Description
AS Assignment

Owner name: XEROX CORPORATION, CONNECTICUT

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:MCCARTHY, ANN L.;BRAUN, KAREN M.;HARRINGTON, STEVEN J.;REEL/FRAME:016180/0052

Effective date: 20041215

AS Assignment

Owner name: JP MORGAN CHASE BANK, TEXAS

Free format text: SECURITY AGREEMENT;ASSIGNOR:XEROX CORPORATION;REEL/FRAME:016761/0158

Effective date: 20030625

Owner name: JP MORGAN CHASE BANK,TEXAS

Free format text: SECURITY AGREEMENT;ASSIGNOR:XEROX CORPORATION;REEL/FRAME:016761/0158

Effective date: 20030625

AS Assignment

Owner name: XEROX CORPORATION, NEW YORK

Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:JPMORGAN CHASE BANK, N.A.;REEL/FRAME:029149/0882

Effective date: 20061204

FPAY Fee payment

Year of fee payment: 4

FEPP

Free format text: MAINTENANCE FEE REMINDER MAILED (ORIGINAL EVENT CODE: REM.)